INDEX

Explanations

references to educational or training programs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tah

-0.15

ambi

-0.15

utin

-0.14

 ones

-0.14

amb

-0.14

edar

-0.14

ambiguous

-0.14

emb

-0.14

esda

-0.13

 lidi

-0.13

POSITIVE LOGITS

0.15

opers

0.14

AKER

0.14

urred

0.14

Zak

0.14

 KÃ¼r

0.13

LOUD

0.13

ieties

0.13

aker

0.13

ART

0.13

Activations Density 1.889%

references to educational or training programs

No Comments

No Known Activations